Machine learning-aided line intensity ratio technique applied to deuterium plasmas

It has been demonstrated that the electron density, ne, and temperature, Te, are successfully evaluated from He I line intensity ratios coupled with machine learning (ML). In this paper, ML-aided ratio technique is applied to deuterium (D) plasmas 0.031 < ne (1018 m−3) 0.67 2.3 Te (eV) 5.1 in PISCES-A linear plasma device. Two ratios, Dα/Dγ Dα/Dβ, used develop a predictive model for separately. Reasonable agreement of both those single Langmuir probe measurements obtained at > 0.1 × 1018 m−3. Addition D2/Dα ratio, where D2 band emission integrated wavelength range λ ∼ 557.4–643.0 nm, found improve prediction of, particular, Te. also confirmed works D 0.067 6.1 0.8 15 another device, PISCES-RF. The two training datasets PISCES-RF combined, unified models give reasonable devices.